Predicting protein residue-residue contacts using deep networks and boosting

被引:115
作者
Eickholt, Jesse [1 ]
Cheng, Jianlin [1 ,2 ,3 ]
机构
[1] Univ Missouri, Dept Comp Sci, Columbia, MO 65211 USA
[2] Univ Missouri, Inst Informat, Columbia, MO 65211 USA
[3] Univ Missouri, C Bond Life Sci Ctr, Columbia, MO 65211 USA
关键词
CORRELATED MUTATIONS; MAPS;
D O I
10.1093/bioinformatics/bts598
中图分类号
Q5 [生物化学];
学科分类号
071010 ; 081704 ;
摘要
Motivation: Protein residue-residue contacts continue to play a larger and larger role in protein tertiary structure modeling and evaluation. Yet, while the importance of contact information increases, the performance of sequence-based contact predictors has improved slowly. New approaches and methods are needed to spur further development and progress in the field. Results: Here we present DNCON, a new sequence-based residue-residue contact predictor using deep networks and boosting techniques. Making use of graphical processing units and CUDA parallel computing technology, we are able to train large boosted ensembles of residue-residue contact predictors achieving state-of-the-art performance.
引用
收藏
页码:3066 / 3072
页数:7
相关论文
共 44 条
[1]   Gapped BLAST and PSI-BLAST: a new generation of protein database search programs [J].
Altschul, SF ;
Madden, TL ;
Schaffer, AA ;
Zhang, JH ;
Zhang, Z ;
Miller, W ;
Lipman, DJ .
NUCLEIC ACIDS RESEARCH, 1997, 25 (17) :3389-3402
[2]   Solving the protein sequence metric problem [J].
Atchley, WR ;
Zhao, JP ;
Fernandes, AD ;
Drüke, T .
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2005, 102 (18) :6395-6400
[3]   The Protein Data Bank [J].
Berman, HM ;
Westbrook, J ;
Feng, Z ;
Gilliland, G ;
Bhat, TN ;
Weissig, H ;
Shindyalov, IN ;
Bourne, PE .
NUCLEIC ACIDS RESEARCH, 2000, 28 (01) :235-242
[4]   Using multi-data hidden Markov models trained on local neighborhoods of protein structure to predict residue-residue contacts [J].
Bjorkholm, Patrik ;
Daniluk, Pawel ;
Kryshtafovych, Andriy ;
Fidelis, Krzysztof ;
Andersson, Robin ;
Hvidsten, Torgeir R. .
BIOINFORMATICS, 2009, 25 (10) :1264-1270
[5]   SCRATCH: a protein structure and structural feature prediction server [J].
Cheng, J ;
Randall, AZ ;
Sweredoski, MJ ;
Baldi, P .
NUCLEIC ACIDS RESEARCH, 2005, 33 :W72-W76
[6]   Improved residue contact prediction using support vector machines and a large feature set [J].
Cheng, Jianlin ;
Baldi, Pierre .
BMC BIOINFORMATICS, 2007, 8 (1)
[7]   Extending CATH: increasing coverage of the protein structure universe and linking structure with function [J].
Cuff, Alison L. ;
Sillitoe, Ian ;
Lewis, Tony ;
Clegg, Andrew B. ;
Rentzsch, Robert ;
Furnham, Nicholas ;
Pellegrini-Calace, Marialuisa ;
Jones, David ;
Thornton, Janet ;
Orengo, Christine A. .
NUCLEIC ACIDS RESEARCH, 2011, 39 :D420-D426
[8]   Deep architectures for protein contact map prediction [J].
Di Lena, Pietro ;
Nagata, Ken ;
Baldi, Pierre .
BIOINFORMATICS, 2012, 28 (19) :2449-2457
[9]   A conformation ensemble approach to protein residue-residue contact [J].
Eickholt, Jesse ;
Wang, Zheng ;
Cheng, Jianlin .
BMC STRUCTURAL BIOLOGY, 2011, 11
[10]   Assessment of domain boundary predictions and the prediction of intramolecular contacts in CASP8 [J].
Ezkurdia, Iakes ;
Grana, Osvaldo ;
Izarzugaza, Jose M. G. ;
Tress, Michael L. .
PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS, 2009, 77 :196-209